Eagle speculative decoding part 4: Add EAGLE2 worker (#2150)

Co-authored-by: kavioyu <kavioyu@tencent.com> Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2025-01-02 19:22:34 +08:00
parent ad20b7957e
commit 815dce0554
6 changed files with 1212 additions and 0 deletions
--- a/test/srt/run_suite.py
+++ b/test/srt/run_suite.py
@@ -13,6 +13,7 @@ suites = {
        "test_abort.py",
        "test_chunked_prefill.py",
        "test_double_sparsity.py",
+        "test_eagle_infer.py",
        "test_embedding_openai_server.py",
        "test_eval_accuracy_mini.py",
        "test_get_weights_by_name.py",